Classical statistical methods, such as p-values, are difficult for researchers to apply correctly. They for example do not allow drawing conclusions from a study early, or for extending a study... Show moreClassical statistical methods, such as p-values, are difficult for researchers to apply correctly. They for example do not allow drawing conclusions from a study early, or for extending a study with extra research groups that want to make their data available later. Sadly, in practice this often leads to faulty application of statistics and subsequent invalidity of experiment conclusions.Partly because of the above, recently, interest in safe, anytime-valid inference (SAVI) with e-values has emerged. This framework offers the same functionality as classical statistics, but also provides researchers with plenty of flexibility, for example through enabling early stopping and effect estimation at any time, extending a study in hindsight, and analyzing data located across multiple hospitals. In this thesis, this theory is further developed for performing SAVI in scenarios applicable to healthcare, specifically for several use-cases in psychiatry. It is explored how one could set up real-time psychiatry research in practice in an automated manner, combining text mining with network analysis techniques for data preparation and exploration and then confirming hypotheses with SAVI. Through this, the work in this thesis contributes to an environment where continuous learning from routinely collected healthcare data for better personalized recommendations is the new standard. Show less
Background Developing predictive models for precision psychiatry is challenging because of unavailability of the necessary data: extracting useful information from existing electronic health record... Show moreBackground Developing predictive models for precision psychiatry is challenging because of unavailability of the necessary data: extracting useful information from existing electronic health record (EHR) data is not straightforward, and available clinical trial datasets are often not representative for heterogeneous patient groups. The aim of this study was constructing a natural language processing (NLP) pipeline that extracts variables for building predictive models from EHRs. We specifically tailor the pipeline for extracting information on outcomes of psychiatry treatment trajectories, applicable throughout the entire spectrum of mental health disorders ("transdiagnostic"). Methods A qualitative study into beliefs of clinical staff on measuring treatment outcomes was conducted to construct a candidate list of variables to extract from the EHR. To investigate if the proposed variables are suitable for measuring treatment effects, resulting themes were compared to transdiagnostic outcome measures currently used in psychiatry research and compared to the HDRS (as a gold standard) through systematic review, resulting in an ideal set of variables. To extract these from EHR data, a semi-rule based NLP pipeline was constructed and tailored to the candidate variables using Prodigy. Classification accuracy and F1-scores were calculated and pipeline output was compared to HDRS scores using clinical notes from patients admitted in 2019 and 2020. Results Analysis of 34 questionnaires answered by clinical staff resulted in four themes defining treatment outcomes: symptom reduction, general well-being, social functioning and personalization. Systematic review revealed 242 different transdiagnostic outcome measures, with the 36-item Short-Form Survey for quality of life (SF36) being used most consistently, showing substantial overlap with the themes from the qualitative study. Comparing SF36 to HDRS scores in 26 studies revealed moderate to good correlations (0.62-0.79) and good positive predictive values (0.75-0.88). The NLP pipeline developed with notes from 22,170 patients reached an accuracy of 95 to 99 percent (F1 scores: 0.38 - 0.86) on detecting these themes, evaluated on data from 361 patients. Conclusions The NLP pipeline developed in this study extracts outcome measures from the EHR that cater specifically to the needs of clinical staff and align with outcome measures used to detect treatment effects in clinical trials. Show less
Preeclampsia is a syndrome of pregnancy characterised by hypertension and proteinuria and occurs in up to 5 percent of pregnant women. The pathophysiology of preeclampsia has not been fully... Show morePreeclampsia is a syndrome of pregnancy characterised by hypertension and proteinuria and occurs in up to 5 percent of pregnant women. The pathophysiology of preeclampsia has not been fully elucidated yet. The endothelium is known to play a key role in the pathogenesis and levels of vascular endothelial growth factor are decreased due to an angiogenic imbalance. In the first part of this thesis, genes associated with preeclampsia were investigated through meta-analysis; genes within the coagulation and immunology domains remained significantly associated with preeclampsia after meta-analysis. In the second and third part of this thesis, the possible role of a key regulator of coagulation and immunology on the endothelium, thrombomodulin, in preeclampsia was investigated in the placenta and the kidney. Diminished placental thrombomodulin expression was associated with the angiogenic imbalance of preeclampsia. Next, in the fourth part of this thesis the interplay between podocytes and endothelial cells in the glomerulus during the anti-angiogenic conditions in preeclampsia was reviewed. In the final part of this thesis the splicing pattern of vascular endothelial growth factor was investigated throughout different examples of glomerular disease. Show less
ABSTRACTObjectiveWomen pregnant after oocyte donation (OD) are prone to develop preeclampsia, a syndrome characterised by an aberrant immunologic response, hypercoagulability and endothelial... Show moreABSTRACTObjectiveWomen pregnant after oocyte donation (OD) are prone to develop preeclampsia, a syndrome characterised by an aberrant immunologic response, hypercoagulability and endothelial dysfunction. A mediator of inflammation and coagulation is thrombomodulin; a possible role player in this syndrome. Our objective is to investigate whether thrombomodulin dysregulation is involved in the development of preeclampsia after OD. DesignCase-control study. SettingWomen who received OD in the LUMC or in the nearby teaching hospitals between 2004 and 2013. Patient(s)A total of 109 placentas of uncomplicated pregnancies (48 naturally conceived, 21 IVF and 40 OD pregnancies) and 16 placentas of OD pregnancies complicated by preeclampsia. Intervention(s)NoneMeasurementsAbundance of thrombomodulin protein and vitamin D receptor (VDR) were determined using immunohistochemistry. mRNA expression was determined using qPCR. Result(s)Placental thrombomodulin protein abundance was lower in OD pregnancies(diffuse pattern in 45%) than in controls(diffuse pattern in 96%;p<0.001). Placental thrombomodulin mRNA expression was lower in OD pregnancies complicated by preeclampsia(0.72±0.47) compared with uncomplicated OD pregnancies(0.43±0.18;p<0.001). Thrombomodulin expression correlated with inflammation and coagulation. VDR expression was decreased in OD pregnancies complicated by preeclampsia and correlated with thrombomodulin mRNA.Conclusion(s) Pregnancies conceived through OD lose placental thrombomodulin expression. This loss is associated with an increased coagulation and inflammation, and indicates that endothelial protection is diminished in OD pregnancies, which might be an explanation for the increased risk for preeclampsia. The vitamin D metabolism is dysregulated in OD pregnancies and might be a target for therapy. Show less